© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20524
    Prev
    Next
    INDEX
    Explanations

    adverbs followed by punctuation or verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    念
    -0.06
    åĴĮçĿ¦
    -0.06
    عÙĪ
    -0.06
    .tt
    -0.06
    okable
    -0.06
    å®ĺ
    -0.06
    stk
    -0.05
     tim
    -0.05
     mult
    -0.05
    éķ¿æľŁçļĦ
    -0.05
    POSITIVE LOGITS
    Dirty
    0.06
     inexp
    0.06
     нам
    0.05
    åIJĦèĩª
    0.05
    hip
    0.05
    Ñħом
    0.05
    åIJĦæī§
    0.05
     independientes
    0.05
     незавиÑģ
    0.05
    ~/
    0.05
    Activations Density 0.005%

    No Known Activations